PAS: Prediction-Based Actuation System for City-Scale Ridesharing Vehicular Mobile Crowdsensing

Xinlei Chen; Susu Xu; Jun Han; Haohao Fu; Xidong Pi; Carlee Joe-Wong; Yong Li; Lin Zhang; Hae Young Noh; Pei Zhang

doi:10.1109/JIOT.2020.2968375

PAS: Prediction-Based Actuation System for City-Scale Ridesharing Vehicular Mobile Crowdsensing

Xinlei Chen, Susu Xu, Jun Han, Haohao Fu, Xidong Pi, Carlee Joe-Wong, Yong Li, Lin Zhang, Hae Young Noh, Pei Zhang

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

38 Citations (Scopus)

Abstract

Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.

Original language	English
Article number	8964368
Pages (from-to)	3719-3734
Number of pages	16
Journal	IEEE Internet of Things Journal
Volume	7
Issue number	5
DOIs	https://doi.org/10.1109/JIOT.2020.2968375
Publication status	Published - 2020 May

Bibliographical note

Funding Information:
Manuscript received July 15, 2019; revised November 4, 2019; accepted January 9, 2020. Date of publication January 21, 2020; date of current version May 12, 2020. This work was supported in part by NSF under Grant CNS1149611, in part by DARPA under Grant D11AP00265, in part by Google, and in part by CMKL. (Xinlei Chen and Susu Xu contributed equally to this work.) (Corresponding author: Xinlei Chen.) Xinlei Chen, Carlee Joe-Wong, and Pei Zhang are with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA (e-mail: xinlei.chen@sv.cmu.edu). Susu Xu and Xidong Pi are with the Department of Civil Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA. Jun Han is with the Department of Computer Science, National University of Singapore, Singapore. Haohao Fu is with the Department of L&S, University of California at Berkeley, Berkeley, CA 94720 USA. Yong Li is with the Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. Lin Zhang is with Tsinghua–Berkeley Shenzhen Institute, Berkeley, CA, USA. Hae Young Noh is with the Department of Civil Engineering, Stanford University, Stanford, CA 94305 USA. Digital Object Identifier 10.1109/JIOT.2020.2968375

Publisher Copyright:
© 2014 IEEE.

All Science Journal Classification (ASJC) codes

Signal Processing
Information Systems
Hardware and Architecture
Computer Science Applications
Computer Networks and Communications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/JIOT.2020.2968375

Cite this

@article{bdbd99b5dfa14bfe81cee3a37367c367,

title = "PAS: Prediction-Based Actuation System for City-Scale Ridesharing Vehicular Mobile Crowdsensing",

abstract = "Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.",

author = "Xinlei Chen and Susu Xu and Jun Han and Haohao Fu and Xidong Pi and Carlee Joe-Wong and Yong Li and Lin Zhang and Noh, {Hae Young} and Pei Zhang",

note = "Funding Information: Manuscript received July 15, 2019; revised November 4, 2019; accepted January 9, 2020. Date of publication January 21, 2020; date of current version May 12, 2020. This work was supported in part by NSF under Grant CNS1149611, in part by DARPA under Grant D11AP00265, in part by Google, and in part by CMKL. (Xinlei Chen and Susu Xu contributed equally to this work.) (Corresponding author: Xinlei Chen.) Xinlei Chen, Carlee Joe-Wong, and Pei Zhang are with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA (e-mail: xinlei.chen@sv.cmu.edu). Susu Xu and Xidong Pi are with the Department of Civil Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA. Jun Han is with the Department of Computer Science, National University of Singapore, Singapore. Haohao Fu is with the Department of L&S, University of California at Berkeley, Berkeley, CA 94720 USA. Yong Li is with the Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. Lin Zhang is with Tsinghua–Berkeley Shenzhen Institute, Berkeley, CA, USA. Hae Young Noh is with the Department of Civil Engineering, Stanford University, Stanford, CA 94305 USA. Digital Object Identifier 10.1109/JIOT.2020.2968375 Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2020",

month = may,

doi = "10.1109/JIOT.2020.2968375",

language = "English",

volume = "7",

pages = "3719--3734",

journal = "IEEE Internet of Things Journal",

issn = "2327-4662",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - PAS

T2 - Prediction-Based Actuation System for City-Scale Ridesharing Vehicular Mobile Crowdsensing

AU - Chen, Xinlei

AU - Xu, Susu

AU - Han, Jun

AU - Fu, Haohao

AU - Pi, Xidong

AU - Joe-Wong, Carlee

AU - Li, Yong

AU - Zhang, Lin

AU - Noh, Hae Young

AU - Zhang, Pei

N1 - Funding Information: Manuscript received July 15, 2019; revised November 4, 2019; accepted January 9, 2020. Date of publication January 21, 2020; date of current version May 12, 2020. This work was supported in part by NSF under Grant CNS1149611, in part by DARPA under Grant D11AP00265, in part by Google, and in part by CMKL. (Xinlei Chen and Susu Xu contributed equally to this work.) (Corresponding author: Xinlei Chen.) Xinlei Chen, Carlee Joe-Wong, and Pei Zhang are with the Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA (e-mail: xinlei.chen@sv.cmu.edu). Susu Xu and Xidong Pi are with the Department of Civil Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA. Jun Han is with the Department of Computer Science, National University of Singapore, Singapore. Haohao Fu is with the Department of L&S, University of California at Berkeley, Berkeley, CA 94720 USA. Yong Li is with the Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. Lin Zhang is with Tsinghua–Berkeley Shenzhen Institute, Berkeley, CA, USA. Hae Young Noh is with the Department of Civil Engineering, Stanford University, Stanford, CA 94305 USA. Digital Object Identifier 10.1109/JIOT.2020.2968375 Publisher Copyright: © 2014 IEEE.

PY - 2020/5

Y1 - 2020/5

N2 - Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.

AB - Vehicular mobile crowdsensing (MCS) enables many smart city applications. Ridesharing vehicle fleets provide promising solutions to MCS due to the advantages of low cost, easy maintenance, high mobility, and long operational time. However, as nondedicated mobile sensing platforms, the first priorities of these vehicles are delivering passengers, which may lead to poor sensing coverage quality. Therefore, to help MCS derive good (large and balanced) sensing coverage quality, an actuation system is required to dispatch vehicles with a limited amount of monetary budget. This article presents PAS, a prediction-based actuation system for city-wide ridesharing vehicular MCS to achieve optimal sensing coverage quality with a limited budget. In PAS, two prediction models forecast probabilities of potential near-future vehicle routes and ride requests across the city. Based on prediction results, a prediction-based actuation planning algorithm is proposed to decide which vehicles to actuate and the corresponding routes. Experiments on city-scale deployments and physical feature-based simulations show that our PAS achieves up to 40% more improvement in sensing coverage quality and up to 20% higher ride request matching rate than baselines. In addition, to achieve a similar level of sensing coverage quality as the baseline, our PAS only needs 10% budget.

UR - http://www.scopus.com/inward/record.url?scp=85083861625&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85083861625&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2020.2968375

DO - 10.1109/JIOT.2020.2968375

M3 - Article

AN - SCOPUS:85083861625

SN - 2327-4662

VL - 7

SP - 3719

EP - 3734

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

IS - 5

M1 - 8964368

ER -

PAS: Prediction-Based Actuation System for City-Scale Ridesharing Vehicular Mobile Crowdsensing

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this